ASSESSING CREDIT RISKIN THE BANKING SECTOR: A COMPARISON OF STATISTICAL AND MCHINE LEARNING (ML)

Abstract

The following analysis aims to compare statistical and ML (Machine Learning) for assessing credit risk. Past literature was analysed critically analyses in order to present the researcher's own opinion related to the factors. Primary quantitative method was used in order to analyse the primary data for the analysis. The findings noted that all of the hypotheses presented in the research were supported; therefore, an MLis a nice factor for analysing credit risk.

It was concluded that risk calculation needs to be fast in order to manage potential threats;therefore incorporation of ML in banking sectors is recommended. Therefore, it can be understood that the factors and benefits of ML for the financial sector are still unpredictable.

Thus from the above analysis, it is understood that ML is an emerging technology that increases the efficiency of risk calculation, however, manual observation is required in order to make appropriate decisions regarding risk.

Keywords:ML, banking sector, financial risk, risk prediction